Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/andrewcigan/vibe-dev-plugin/lessonsnpx skills add andrewcigan/vibe-dev-plugin --skill lessonsgit clone --depth 1 https://github.com/andrewcigan/vibe-dev-pluginWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00051 | $0.00917 |
| Opus 5 | $0.00026 | $0.00458 |
| Sonnet 5 | $0.00010 | $0.00183 |
| Haiku 4.5 | $0.00005 | $0.00092 |
Grade B, and why
lessons scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/memory/MEMORY.md How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/lessons [export]
Управление подсистемой Learning — журнал ошибок и зафиксированные уроки.
По умолчанию (без аргументов): показать
Active errors (этой фазы / последние 30 дней)
# Парсим error-journal.md
# Показываем последние записи + статус promotion
Формат вывода в SESSION.md или в чате:
📓 Errors этой фазы: 7
Top-3 классы ошибок:
1. api_research (3) — закрыто? да (feedback_api_research_first.md)
2. concurrent_write (2) — закрыто? да (feedback_concurrent_writes.md)
3. scope_leak (2) — НЕ закрыто (нужен pre-commit hook)
Recurrence rate: 0% ✓ (или X% ⚠️)
Error velocity: 1.4/неделя
Promoted lessons (память проекта)
ls ~/.claude/projects/<dashed-path>/memory/feedback_*.md
Показать список:
📚 Lessons в памяти проекта: <count>
- feedback_api_research_first.md (4 KB) — главный урок из проекта с документным ассистентом
- feedback_concurrent_writes.md (1.5 KB)
- feedback_no_technical_choices.md (3 KB)
- ...
Глобальные уроки (применимые к пользователю)
cat ~/.claude/memory/MEMORY.md
С аргументом export: выгрузить
/lessons export — собирает всё в один документ для анализа:
mkdir -p ~/.vibe-dev/retrospectives/YYYY-MM-DD-<project>-export/
cd ~/.vibe-dev/retrospectives/YYYY-MM-DD-<project>-export/
# Объединить
cat \
<project>/error-journal.md \
~/.claude/projects/<dashed-path>/memory/MEMORY.md \
~/.claude/projects/<dashed-path>/memory/feedback_*.md \
> ALL_LESSONS_<project>.md
# Создать summary
echo "# Lessons Summary <project>" > SUMMARY.md
echo "" >> SUMMARY.md
echo "Generated: $(date)" >> SUMMARY.md
# ... группировка по классам, частоте, severity
Файлы:
ALL_LESSONS_<project>.md— полный архивSUMMARY.md— сводка с группировкойRECURRENCE_ANALYSIS.md— что повторялось и почему
С аргументом add "<urok>": вручную добавить урок
/lessons add "при работе с Telegram-ботами всегда использовать webhook не polling":
- Создать
feedback_<auto_slug>.mdв~/.claude/projects/.../memory/ - Добавить строку в MEMORY.md этого проекта
- Спросить пользователя: «Это применимо ко всем твоим проектам? Если да — добавлю в ~/CLAUDE.md»
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 104 lines · 51 tokens per session scan B 035fcb264103
lessons is a skill published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 917 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
harness-engineering-guide
Audit, design, and implement AI agent harnesses for any codebase. A harness is the constraints, feedback loops, and verification systems surrounding AI coding agents — improving it is the highest-leverage way to improve AI code quality. Three modes: Audit (scorecard), Implement (set up components), Design (full…
google-drive-sheets
Find, read, export, edit, and manage the user's Google Drive, Docs, Sheets, and Slides through per-user OAuth.
github-gitlab
Work with GitHub and GitLab repositories through resident gh/glab/git auth on the agent computer.
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
commit-push-pr
Commit selected local changes, push the branch, and create or update a GitHub pull request with BitFun attribution. Use when the user asks to 提交 PR、提代码、commit and push、开 PR、create a pull request, or wants a Claude Code-like one-command PR publishing flow from BitFun.